Connectionist Representations of Tonal Music

Until now, artificial neural networks have been used to capture only the informal properties of music. However, cognitive scientist Michael Dawson found that by training artificial neural networks to make basic judgments concerning tonal music, such as identifying the tonic of a scale or the quality of a musical chord, the networks revealed formal musical properties that differ dramatically from those typically presented in Western music theory. For example, where Western music theory identifies twelve distinct notes or pitch-classes, trained artificial neural networks-listening to the same musical examples-treat notes as if they belong to only three or four pitch-classes, a wildly different interpretation of the components of tonal music. To introduce readers to the use of artificial neural networks in the study of music, Dawson presents numerous case studies and research findings that address problems related to training a neural network to identify scales and keys, classify musical chords, and learn jazz chord progressions. But it is in his detailed analysis of the musical patterns discovered by the networks that Dawson yields important contributions to the field of music cognition and presents new possibilities for the theoretical study of tonal music.